kümeleme

1. Kütüphanelerin Yüklenmesi

library(readr)
library(tidyverse)
library(tidyr)
library(dendextend)
library(knitr)
library(gridExtra)
library(ggplot2)
library(VIM)
library(corrplot)
library(car)
library(ResourceSelection)
library(glmulti)
library(tree)
library(randomForest)
library(ISLR)
library(class)
library(pROC)
library(gtools)
library(tidyverse)
library(GGally)
library(superml)
library(caret)
library(Boruta)
library("stringr")
library("tidyr")
library("readr")
library("here")
library("skimr")
library("janitor")
library("lubridate")
library(gridExtra)
library(ggplot2)
library(VIM)
library(corrplot)
library(car)
library(ResourceSelection)
library(glmulti)
library(tree)
library(randomForest)
library(ISLR)
library(class)
library(pROC)
library(gtools)
library(tidyverse)
library("scales")
library("ggcorrplot")
library("ggrepel")
library("forcats")
library("corrgram")
library(tidymodels)
library(baguette)
library(discrim)
library(bonsai)
library(ResourceSelection)
library(kableExtra)
library(broom)
library(dplyr)
library(caret)
library(tidyr)
library(corrplot)
library("Hmisc")
library(psych)
library(factoextra)
library("DescTools")
library(ResourceSelection)
library(haven)
library(effectsize)
library(rstatix)
library(ggpubr)
library(biotools)
library(PerformanceAnalytics)
library(heplots)
library(gplots)

clean_df <- read.csv('/home/ilke/Downloads/clean_heart.csv')

10.Kümeleme

10.1 Hiyerarşik Kümeleme

h_kume <- clean_df[, c("Age","RestingBP","Cholesterol","MaxHR","Oldpeak")]
h_kumee <- scale(h_kume)
# Korelasyon matrisinin incelenmesi
rcorr(as.matrix(h_kume),type="pearson") 

##               Age RestingBP Cholesterol MaxHR Oldpeak
## Age          1.00      0.27        0.07 -0.40    0.28
## RestingBP    0.27      1.00        0.09 -0.13    0.19
## Cholesterol  0.07      0.09        1.00  0.00    0.07
## MaxHR       -0.40     -0.13        0.00  1.00   -0.28
## Oldpeak      0.28      0.19        0.07 -0.28    1.00
## 
## n= 702 
## 
## 
## P
##             Age    RestingBP Cholesterol MaxHR  Oldpeak
## Age                0.0000    0.0656      0.0000 0.0000 
## RestingBP   0.0000           0.0176      0.0006 0.0000 
## Cholesterol 0.0656 0.0176                0.9528 0.0576 
## MaxHR       0.0000 0.0006    0.9528             0.0000 
## Oldpeak     0.0000 0.0000    0.0576      0.0000

# Hiyerarsik Kümeleme
d <- dist(h_kume, method = "euclidean") # uzaklik matrisi
fit <- hclust(d, method="ward.D") # method= "single", "complete", "average", "ward.D", "centroid"
dend<-as.dendrogram(fit) # Dendogram çizimi
plot(dend)

plot(color_branches(dend, k=4))

10.2 K-Means

h_kume <- scale(h_kume)
fviz_nbclust(h_kume, kmeans, method = "wss")

fviz_nbclust(h_kume, kmeans, method = "silhouette")

set.seed(95739487) 
km.res <- kmeans(h_kume,2, iter.max=100, algorithm="Lloyd")### i
t(km.res$centers) 

##                      1          2
## Age         -0.5304542  0.6985189
## RestingBP   -0.3629667  0.4779661
## Cholesterol -0.1887484  0.2485498
## MaxHR        0.4867892 -0.6410194
## Oldpeak     -0.4939088  0.6503948

library(cluster)
clusplot(h_kume, km.res$cluster, main='2D representation of the Cluster solution',
         color=TRUE, shade=TRUE,
         labels=2, lines=0)